Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.0305. Min Range: -2.0305

Max Act: 2.0305. Min Act: -0.1700

Data Index: 4692757 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.9774. Min Act: -0.1700

Data Index: 3449247 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.9507. Min Act: -0.1700

Data Index: 2586988 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.8266. Min Act: -0.1700

Data Index: 1889303 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7960. Min Act: -0.1700

Data Index: 813021 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.8038. Min Act: -0.1700

Data Index: 8123745 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7788. Min Act: -0.1700

Data Index: 5814499 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7997. Min Act: -0.1700

Data Index: 3359484 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7817. Min Act: -0.1700

Data Index: 1437929 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7664. Min Act: -0.1700

Data Index: 1659013 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7663. Min Act: -0.1700

Data Index: 8597987 (Open Web Text)

Max Activating Token Index: 172

Text #11

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7739. Min Act: -0.1700

Data Index: 1505825 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7730. Min Act: -0.1700

Data Index: 7602662 (Open Web Text)

Max Activating Token Index: 822

Text #13

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7510. Min Act: -0.1700

Data Index: 1766325 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7589. Min Act: -0.1700

Data Index: 4632461 (Open Web Text)

Max Activating Token Index: 56

Text #15

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7441. Min Act: -0.1700

Data Index: 3454013 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7634. Min Act: -0.1700

Data Index: 4797216 (Open Web Text)

Max Activating Token Index: 50

Text #17

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7408. Min Act: -0.1700

Data Index: 6642342 (Open Web Text)

Max Activating Token Index: 72

Text #18

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7705. Min Act: -0.1700

Data Index: 2579200 (Open Web Text)

Max Activating Token Index: 250

Text #19

Max Range: 2.0305. Min Range: -2.0305

Max Act: 1.7378. Min Act: -0.1700

Data Index: 1335528 (Open Web Text)

Max Activating Token Index: 861